[all-commits] [llvm/llvm-project] c5b4a2: [X86] Use zero vector to extend to 512-bits for st...

[topperc via All-commits]

  Branch: refs/heads/master
  Home:   https://github.com/llvm/llvm-project
  Commit: c5b4a2386b51a18daad7e42040c685c2e9708c47
      https://github.com/llvm/llvm-project/commit/c5b4a2386b51a18daad7e42040c685c2e9708c47
  Author: Craig Topper <craig.topper at gmail.com>
  Date:   2019-12-25 (Wed, 25 Dec 2019)

  Changed paths:
    M llvm/lib/Target/X86/X86ISelLowering.cpp
    M llvm/test/CodeGen/X86/vec-strict-fptoint-128.ll

  Log Message:
  -----------
  [X86] Use zero vector to extend to 512-bits for strict_fp_to_uint v2i1->v2f64 on targets with AVX512F, but not AVX512VL.

In the worst case, this requires a 128-bit move instruction to
implicitly zero the upper bits. In the common case, we should
recognize the producing instruction already zeroed the upper bits.